cloud-fan commented on a change in pull request #28102: [SPARK-31327][SQL] Write Spark version into Avro file metadata URL: https://github.com/apache/spark/pull/28102#discussion_r402720616
########## File path: external/avro/src/main/java/org/apache/spark/sql/avro/SparkAvroKeyOutputFormat.java ########## @@ -0,0 +1,92 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.avro; + +import java.io.IOException; +import java.io.OutputStream; +import java.util.Map; + +import org.apache.avro.Schema; +import org.apache.avro.file.CodecFactory; +import org.apache.avro.file.DataFileWriter; +import org.apache.avro.generic.GenericData; +import org.apache.avro.generic.GenericRecord; +import org.apache.avro.mapred.AvroKey; +import org.apache.avro.mapreduce.AvroKeyOutputFormat; +import org.apache.avro.mapreduce.Syncable; +import org.apache.hadoop.io.NullWritable; +import org.apache.hadoop.mapreduce.RecordWriter; +import org.apache.hadoop.mapreduce.TaskAttemptContext; + +// A variant of `AvroKeyOutputFormat`, which is used to inject the custom `RecordWriterFactory` so +// that we can set avro file metadata. +public class SparkAvroKeyOutputFormat extends AvroKeyOutputFormat<GenericRecord> { + public SparkAvroKeyOutputFormat(Map<String, String> metadata) { + super(new SparkRecordWriterFactory(metadata)); + } + + static class SparkRecordWriterFactory extends RecordWriterFactory<GenericRecord> { + private final Map<String, String> metadata; + SparkRecordWriterFactory(Map<String, String> metadata) { + this.metadata = metadata; + } + + protected RecordWriter<AvroKey<GenericRecord>, NullWritable> create( + Schema writerSchema, + GenericData dataModel, + CodecFactory compressionCodec, + OutputStream outputStream, + int syncInterval) throws IOException { + return new SparkAvroKeyRecordWriter( + writerSchema, dataModel, compressionCodec, outputStream, syncInterval, metadata); + } + } +} + +// This a fork of org.apache.avro.mapreduce.AvroKeyRecordWriter, in order to set file metadata. +class SparkAvroKeyRecordWriter<T> extends RecordWriter<AvroKey<T>, NullWritable> + implements Syncable { + private final DataFileWriter<T> mAvroFileWriter; + public SparkAvroKeyRecordWriter( + Schema writerSchema, + GenericData dataModel, + CodecFactory compressionCodec, + OutputStream outputStream, + int syncInterval, + Map<String, String> metadata) throws IOException { + this.mAvroFileWriter = new DataFileWriter(dataModel.createDatumWriter(writerSchema)); + for (Map.Entry<String, String> entry : metadata.entrySet()) { + this.mAvroFileWriter.setMeta(entry.getKey(), entry.getValue()); + } Review comment: yup ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
